Nessus MCP Server
An MCP server for interacting with the Tenable Nessus vulnerability scanner.
Nessus MCP Server
A Model Context Protocol (MCP) server for interacting with the Tenable Nessus vulnerability scanner. This server allows AI assistants to perform vulnerability scanning and analysis through the MCP protocol.
Features
- Vulnerability Scanning: Start and monitor vulnerability scans against specified targets
- Scan Management: List, track, and retrieve results from vulnerability scans
- Vulnerability Analysis: Search for and get detailed information about specific vulnerabilities
- Mock Mode: Fully functional mock mode for testing without a Nessus API key
Tools
The server provides the following tools:
| Tool Name | Description |
|---|---|
list_scan_templates | List available Nessus scan templates |
start_scan | Start a new vulnerability scan against a target |
get_scan_status | Check the status of a running scan |
get_scan_results | Get the results of a completed scan |
list_scans | List all scans and their status |
get_vulnerability_details | Get detailed information about a specific vulnerability |
search_vulnerabilities | Search for vulnerabilities by keyword |
Installation
Prerequisites
- Node.js 16 or higher
- TypeScript (for development)
Building from Source
-
Clone the repository:
git clone https://github.com/Cyreslab-AI/nessus-mcp-server.git cd nessus-mcp-server -
Install dependencies:
npm install -
Build the server:
npm run build
Usage
Running in Mock Mode
By default, the server runs in mock mode, which doesn't require a Nessus API key:
node build/index.js
Running with Nessus API
To connect to a real Nessus instance, set the following environment variables:
NESSUS_URL=https://your-nessus-instance:8834
NESSUS_ACCESS_KEY=your-access-key
NESSUS_SECRET_KEY=your-secret-key
Then run the server:
node build/index.js
Using with Claude for Desktop
To use this server with Claude for Desktop:
-
Edit your Claude for Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
Add the server configuration:
{
"mcpServers": {
"nessus": {
"command": "node",
"args": ["/path/to/nessus-mcp-server/build/index.js"],
"env": {
"NESSUS_URL": "https://your-nessus-instance:8834",
"NESSUS_ACCESS_KEY": "your-access-key",
"NESSUS_SECRET_KEY": "your-secret-key"
}
}
}
}
For mock mode, you can omit the env section.
Example Interactions
Starting a Scan
start_scan:
target: 192.168.1.1
scan_type: basic-network-scan
Getting Scan Results
get_scan_results:
scan_id: scan-1234567890
Searching for Vulnerabilities
search_vulnerabilities:
keyword: log4j
Development
Project Structure
src/index.ts: Main server entry pointsrc/nessus-api.ts: Nessus API client with mock fallbacksrc/mock-data.ts: Mock vulnerability data for testingsrc/tools/: Tool implementationssrc/utils/: Utility functions
Adding New Tools
- Define the tool schema and handler in the appropriate file in
src/tools/ - Import and register the tool in
src/index.ts
License
MIT
Disclaimer
This server is not affiliated with or endorsed by Tenable. Nessus is a trademark of Tenable, Inc.
관련 서버
Alpha Vantage MCP Server
스폰서Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Playwright IA: Midscene.js
Automate Playwright flows using natural language with Midscene.js and AI.
Valar API MCP
Integrate with the Valar API, assisting frontend developers with API documentation and endpoint discovery.
MCPfinder
A Node.js server for AI agents to discover, install, and manage new capabilities on demand via the MCP protocol.
Explorium API
Interact with the Explorium API to access external data for machine learning.
MCP Servers Collection
A collection of MCP servers providing structured interfaces for AI assistants to interact with various development tools and services.
NeuroDev MCP Server
A powerful Model Context Protocol (MCP) server that supercharges your Python development workflow with AI-powered code review, intelligent test generation, and comprehensive test execution.
BlenderMCP
Connects Blender to AI models via MCP for prompt-assisted 3D modeling, scene creation, and manipulation.
Contentrain MCP
Extract, govern, and ship structured content from your codebase.
MCP Server on Cloudflare
A template for deploying a remote MCP server on Cloudflare Workers without authentication.
mcp-of-mcps
MCP of MCPs is a meta-server that merges all your MCP servers into a single smart endpoint. It gives AI agents instant tool discovery, selective schema loading, and massively cheaper execution, so you stop wasting tokens and time. With persistent tool metadata, semantic search, and direct code execution between tools, it turns chaotic multi-server setups into a fast, efficient, hallucination-free workflow. It also automatically analyzes the tools output schemas if not exist and preserves them across sessions for consistent behavior.